Files in this item



application/pdfECE499-Sp2012-nath.pdf (2MB)Restricted to U of Illinois
(no description provided)PDF


Title:Combat Humanoid Robotics
Author(s):Nath, Vishnu
Contributor(s):Levinson, Stephen
artificial intelligence
humanoid robots
machine learning
cognitive models
machine learning algorithms
Abstract:My research deals with incorporating Artificial Intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a robot to fire a gun by allowing it to make small errors and then rectifying them with each iteration. After a couple of iterations, the robot would be able to fire at the target any number of times. The number of iterations that we reached was 3 to 4. After that, the robot had an accuracy tending to 100%. The learning algorithm is bifurcated into two options. The selection criterion for choosing the algorithm is the dynamics of the target. If the target is stationery, a least mean square (LMS) approach is used. If it is a moving target, a modified Q Learning approach would be best. The vision system incorporates a Gaussian mixture model (GMM) to determine the center of the target and the point of impact of the bullet. The major application of this project is in the defense sector since soldiers would not have to march into the warzone any longer. The military would be able to deploy these droids that have incredible accuracy, thus saving human lives.
Issue Date:2012-05
Publication Status:unpublished
Peer Reviewed:not peer reviewed
Date Available in IDEALS:2014-01-09

This item appears in the following Collection(s)

Item Statistics